Lab 4

library(ggplot2)
SNPs<- read.table("23andMe_complete.txt", header= TRUE, sep = "\t")

1

ex <- ggplot(data = SNPs) +
  geom_bar(mapping = aes(x = chromosome), fill="blue")
ex + ggtitle("Chromosome Count") +
  xlab("Chromosome Number") +
  ylab("Nucleotide Count")

2

nt <- c("AA"="blue","AC"="blue","AG"="blue","AT"="blue","CC"="blue","CG"="blue","CT"="blue","GG"="blue","GT"="blue","TT"="blue","A"="red","G"="red","T"="red","C"="red","--"="yellow","D"="yellow","DD"="yellow","DI"="yellow","I"="yellow","II"="yellow")
SNPs$chromosome = ordered(SNPs$chromosome, levels=c(seq(1, 22), "X", "Y", "MT"))
ggplot(data = SNPs) +
  geom_bar(mapping = aes(x = chromosome, fill=genotype)) +
             scale_fill_manual(values=nt) +
             ggtitle("Chromosome Count by Genotype") +
             xlab("Chromosome Number") +
              ylab("Nucleotide Count by Genotype")

3

ppi <- 300
png("SNP_ex3.png", width=6*ppi, res=ppi)
SNPs$chromosome = ordered(SNPs$chromosome, levels=c(seq(1, 22), "X", "Y", "MT"))
SNP <- ggplot(data = SNPs) +
  geom_bar(mapping = aes(x = chromosome, fill = genotype), position = "dodge")
dev.off()

## quartz_off_screen 
##                 2

Genotype counts per chromosome

4

SNPs$chromosome = ordered(SNPs$chromosome, levels=c(seq(1, 22), "X", "Y", "MT"))
wrap <- ggplot(data = SNPs) +
  geom_bar(mapping = aes(x = chromosome, fill = genotype), position = "dodge") +
  facet_wrap(~ genotype, ncol = 3)
wrap + ggtitle("Genotype Frequencies on Chromosomes") +
  xlab("Chromosome Number") +
  ylab("Genotype Count")

5

library(plotly)

## 
## Attaching package: 'plotly'

## The following object is masked from 'package:ggplot2':
## 
##     last_plot

## The following object is masked from 'package:stats':
## 
##     filter

## The following object is masked from 'package:graphics':
## 
##     layout

SNPs$chromosome = ordered(SNPs$chromosome, levels=c(seq(1, 22), "X", "Y", "MT"))
ggplotly(
  ggplot(data = SNPs) +
    geom_bar(mapping = aes(x = chromosome, fill = genotype), position = "dodge") +
    facet_wrap(~ genotype, nrow = 2)
)

6

YSNP <- subset(SNPs, chromosome=="Y")
library(DT)
datatable(YSNP)

## Warning in instance$preRenderHook(instance): It seems your data is too big
## for client-side DataTables. You may consider server-side processing: https://
## rstudio.github.io/DT/server.html